© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 140656
    Prev
    Next
    INDEX
    Explanations

    programming sections

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     지구
    0.43
     table
    0.40
     nike
    0.40
     Finalmente
    0.40
    edere
    0.40
     봐
    0.38
    стки
    0.38
    席
    0.38
     Bewertungen
    0.37
     문의
    0.37
    POSITIVE LOGITS
    uresh
    0.38
    Dom
    0.36
    ှ
    0.35
     routinely
    0.35
     palt
    0.35
    pad
    0.35
    㳑
    0.35
    kla
    0.34
     వెం
    0.34
    UPA
    0.34
    Activations Density 0.001%

    No Known Activations